mihailotim-db commented on code in PR #50304:
URL: https://github.com/apache/spark/pull/50304#discussion_r2003581847
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala:
##########
@@ -1031,18 +1036,39 @@ class Analyzer(override val catalogManager:
CatalogManager) extends RuleExecutor
private def addMetadataCol(
plan: LogicalPlan,
- requiredAttrIds: Set[ExprId]): LogicalPlan = plan match {
+ requiredAttrIds: Set[ExprId],
+ onlyUniqueAndNecessaryMetadataColumns: Boolean = true): LogicalPlan =
plan match {
case s: ExposesMetadataColumns if s.metadataOutput.exists( a =>
requiredAttrIds.contains(a.exprId)) =>
s.withMetadataColumns()
case p: Project if p.metadataOutput.exists(a =>
requiredAttrIds.contains(a.exprId)) =>
+ val existingExprIds = new util.HashSet[ExprId]
+ p.projectList.foreach(attr => existingExprIds.add(attr.exprId))
+
+ val uniqueMetadataColumns = if (onlyUniqueAndNecessaryMetadataColumns)
{
+ p.metadataOutput.collect {
+ case attr
+ if requiredAttrIds.contains(attr.exprId) && !existingExprIds
+ .contains(attr.exprId) =>
+ existingExprIds.add(attr.exprId)
+ attr.markAsAllowAnyAccess()
+ }
+ } else {
+ p.metadataOutput.map(_.markAsAllowAnyAccess())
+ }
+
val newProj = p.copy(
// Do not leak the qualified-access-only restriction to normal plan
outputs.
- projectList = p.projectList ++
p.metadataOutput.map(_.markAsAllowAnyAccess()),
- child = addMetadataCol(p.child, requiredAttrIds))
+ projectList = p.projectList ++ uniqueMetadataColumns,
Review Comment:
Done!
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala:
##########
@@ -1031,18 +1036,39 @@ class Analyzer(override val catalogManager:
CatalogManager) extends RuleExecutor
private def addMetadataCol(
plan: LogicalPlan,
- requiredAttrIds: Set[ExprId]): LogicalPlan = plan match {
+ requiredAttrIds: Set[ExprId],
+ onlyUniqueAndNecessaryMetadataColumns: Boolean = true): LogicalPlan =
plan match {
case s: ExposesMetadataColumns if s.metadataOutput.exists( a =>
requiredAttrIds.contains(a.exprId)) =>
s.withMetadataColumns()
case p: Project if p.metadataOutput.exists(a =>
requiredAttrIds.contains(a.exprId)) =>
+ val existingExprIds = new util.HashSet[ExprId]
+ p.projectList.foreach(attr => existingExprIds.add(attr.exprId))
+
+ val uniqueMetadataColumns = if (onlyUniqueAndNecessaryMetadataColumns)
{
Review Comment:
Ah very nice, done!
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala:
##########
@@ -1031,18 +1036,39 @@ class Analyzer(override val catalogManager:
CatalogManager) extends RuleExecutor
private def addMetadataCol(
plan: LogicalPlan,
- requiredAttrIds: Set[ExprId]): LogicalPlan = plan match {
+ requiredAttrIds: Set[ExprId],
+ onlyUniqueAndNecessaryMetadataColumns: Boolean = true): LogicalPlan =
plan match {
case s: ExposesMetadataColumns if s.metadataOutput.exists( a =>
requiredAttrIds.contains(a.exprId)) =>
s.withMetadataColumns()
case p: Project if p.metadataOutput.exists(a =>
requiredAttrIds.contains(a.exprId)) =>
+ val existingExprIds = new util.HashSet[ExprId]
+ p.projectList.foreach(attr => existingExprIds.add(attr.exprId))
+
+ val uniqueMetadataColumns = if (onlyUniqueAndNecessaryMetadataColumns)
{
+ p.metadataOutput.collect {
+ case attr
+ if requiredAttrIds.contains(attr.exprId) && !existingExprIds
+ .contains(attr.exprId) =>
+ existingExprIds.add(attr.exprId)
Review Comment:
We never actually guarantee that we won't have duplicate `ExprIds` in
metadata output, we just inherit from below and append the new ones. Maybe
instead of enforcing this here, we should enforce uniqueness when creating
metadata?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
